emperor-verify SKILL.md skillA
emperor-verify from arbi-elezi/emperor-time is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arbi-elezi/emperor-time/emperor-verify@v0.4.27Pins v0.4.27 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arbi-elezi/emperor-time
- Path
skills/emperor-verify/SKILL.md- Versions recorded
- 5
- Latest version
- v0.4.27, committed Sep 29, 2026
- First version recorded
- Sep 28, 2026
- Size
- 5,378 bytes
- Repository stars
- 3
- License
- MIT
Emperor Time — VERIFY / review / critique. Claim audit, eight-count self-critique, isolated hetero-critique, request-review HARD-GATE, receive-review HARD-GATE, verification-before-completion / evidence HARD-GATE, claim-audit HARD-GATE, critique eight-count HARD-GATE, verdict/breach HARD-GATE (G5), mechanical G4/G5. Use when reviewing a diff, requesting code review, claiming tests pass, saying done / fixed / green, or before commit/PR/deliver/merge.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Emperor Verify (Judgment wrapper) ## MUST — critique eight-count HARD-GATE before G4 Before opening G4, run `scripts/emperor critique <task-dir>` (or `self-critique`). Doctrine: `chains/judgment-chain/self-critique.md`. Missing axes / empty Checked cells / critique-file-present theater → exit 1. G4 calls `scripts/lib/critique.py`; a critique file alone is theater. ## MUST — claim-audit HARD-GATE before G4 Before opening G4, run `scripts/emperor claim-audit <task-dir>` (or `judgment-audit`). Doctrine: `chains/judgment-chain/claim-audit.md`. Missing CLAIM AUDIT line / unfinished HYPOTHESIS|TESTED → exit 1. G4 calls `scripts/lib/claim_audit.py`; a critique file alone is theater. ## MUST — request-review checklist first Before merge to main, after a major feature, and after each subagent-driven task, open `skills/emperor-verify/request-review-checklist.md` (Chain Jail leaf from Superpowers `requesting-code-review` → When / How / Act-on-feedback only) and/or run `scripts/emperor review` (prints the mechanical REVIEW / STEP / MUST card). No author self-review in place of dispatch. Do not load whole `requesting-code-review`; ET + emperor-verify orchestrate. …
Read the whole file at its exact version.
How to install
mdr add arbi-elezi/emperor-time/emperor-verify@sha256:2d7611ef31b8840eThe line at the top of this page pins the label v0.4.27, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ubdzuczuiqvpuwxp)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 28, 2026 and Sep 29, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.4.27 latest | 2026-09-29 | 3f42630 | 5,378 B | A | view · diff |
| v0.4.27 | 2026-09-29 | d159e1a | 5,301 B | A | view · diff |
| v0.4.27 | 2026-09-29 | 436eee8 | 5,283 B | A | view · diff |
| v0.4.27 | 2026-09-28 | b598fdd | 5,007 B | A | view · diff |
| v0.4.27 | 2026-09-28 | a10fd27 | 4,916 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5378 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
arbi-elezi/emperor-time · 3 stars · license MIT · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ubdzuczuiqvpuwxp GET https://markdownregistry.com/api/v1/resolve?ref=arbi-elezi/emperor-time/emperor-verify GET https://markdownregistry.com/api/v1/blob/2d7611ef31b8840e9757f897b5ed12241d7e37c424c85f77170c43b0e1e758e3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.